Activate a window (bring it to the foreground) by matching its title. Args: title_pattern: Pattern to match window title use_regex: If True, treat the pattern as a regex, otherwise use fuzzy matching threshold: Minimum score (0-100) required for a fuzzy match Returns: Success or error message
AI agents invoke activate_window to trigger actions in Computer Control MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation — bringing a window to the foreground — which affects the state of the desktop environment. It doesn't just read data; it actively changes window focus/state. This constitutes an Execute-level action as it manipulates the OS UI state. Misuse could cause an AI agent to redirect user attention or interact with unintended windows, enabling further misuse of other tools.
From the tool's definition Activate a window (bring it to the foreground) by matching its title
Documented attack patterns abuse exactly the kind of access activate_window gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Computer Control MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for activate_window:
{
"version": "1",
"default": "deny",
"tools": {
"activate_window": {
"limits": [
{
"counter": "activate_window_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}activate_window stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Activate a window (bring it to the foreground) by matching its title. Args: title_pattern: Pattern to match window title use_regex: If True, treat the pattern as a regex, otherwise use fuzzy matching threshold: Minimum score (0-100) required for a fuzzy match Returns: Success or error message. It is categorised as a Execute tool in the Computer Control MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Computer Control MCP server in PolicyLayer and add a rule for activate_window: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Computer Control MCP. Nothing to install.
activate_window is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the activate_window rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for activate_window. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
activate_window is provided by the Computer Control MCP server (ab498/computer-control-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 15 Computer Control MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
15 Computer Control MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.